{"id":"https://openalex.org/W4416965834","doi":"https://doi.org/10.1109/tmm.2025.3640020","title":"A Fusion-Enhanced Network for Infrared and Visible High-Level Vision Tasks","display_name":"A Fusion-Enhanced Network for Infrared and Visible High-Level Vision Tasks","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416965834","doi":"https://doi.org/10.1109/tmm.2025.3640020"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3640020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3640020","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102894859","display_name":"Fangcen Liu","orcid":"https://orcid.org/0000-0002-1845-9907"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangcen Liu","raw_affiliation_strings":["School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-1845-9907","affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021881939","display_name":"Chenqiang Gao","orcid":"https://orcid.org/0000-0003-4174-4148"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenqiang Gao","raw_affiliation_strings":["School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, P.R. China","School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-4174-4148","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, P.R. China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400042","display_name":"Fang Chen","orcid":"https://orcid.org/0000-0003-4899-8474"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Chen","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, School of Engineering, University of California, Merced, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4899-8474","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, School of Engineering, University of California, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432307","display_name":"Pengcheng Li","orcid":"https://orcid.org/0000-0002-0691-7966"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Li","raw_affiliation_strings":["School of Computer Science and Technology, Hainan University, Haikou, China"],"raw_orcid":"https://orcid.org/0000-0002-0691-7966","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University, Haikou, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063770728","display_name":"Junjie Guo","orcid":"https://orcid.org/0009-0005-8957-8419"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Guo","raw_affiliation_strings":["School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0005-8957-8419","affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091017287","display_name":"Deyu Meng","orcid":"https://orcid.org/0000-0002-1294-8283"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyu Meng","raw_affiliation_strings":["School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China","School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, Shanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-1294-8283","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, Shanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35084545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"1469","last_page":"1482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8278999924659729,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8278999924659729,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.07119999825954437,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.03669999912381172,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6539999842643738},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5756999850273132},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5382999777793884},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4666000008583069},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.46459999680519104},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44780001044273376},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4374000132083893},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.42320001125335693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486999869346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6561999917030334},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5756999850273132},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5382999777793884},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5047000050544739},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3847000002861023},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2741999924182892},{"id":"https://openalex.org/C158355884","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Infrared","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3640020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3640020","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5184008313","display_name":null,"funder_award_id":"62176035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7385732726","display_name":null,"funder_award_id":"JCYJ20240813151216022","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G8450138976","display_name":null,"funder_award_id":"62201111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W2774839435","https://openalex.org/W2884822772","https://openalex.org/W2887486131","https://openalex.org/W2945809413","https://openalex.org/W2963150697","https://openalex.org/W3039479109","https://openalex.org/W3091001089","https://openalex.org/W3118570274","https://openalex.org/W3159018159","https://openalex.org/W3163132162","https://openalex.org/W3166016280","https://openalex.org/W3170885821","https://openalex.org/W3209519737","https://openalex.org/W3213472242","https://openalex.org/W4200635035","https://openalex.org/W4220849367","https://openalex.org/W4220893768","https://openalex.org/W4285205872","https://openalex.org/W4296913506","https://openalex.org/W4312594135","https://openalex.org/W4312685069","https://openalex.org/W4313007055","https://openalex.org/W4313156423","https://openalex.org/W4313270788","https://openalex.org/W4313639507","https://openalex.org/W4315606099","https://openalex.org/W4316654064","https://openalex.org/W4319879007","https://openalex.org/W4321483876","https://openalex.org/W4366352735","https://openalex.org/W4366378409","https://openalex.org/W4367147113","https://openalex.org/W4367663172","https://openalex.org/W4376872192","https://openalex.org/W4379209584","https://openalex.org/W4379528676","https://openalex.org/W4382119971","https://openalex.org/W4385801610","https://openalex.org/W4386038403","https://openalex.org/W4386057769","https://openalex.org/W4386065698","https://openalex.org/W4386076015","https://openalex.org/W4386076504","https://openalex.org/W4386076522","https://openalex.org/W4386083029","https://openalex.org/W4386179772","https://openalex.org/W4386189887","https://openalex.org/W4387969358","https://openalex.org/W4388191449","https://openalex.org/W4389491034","https://openalex.org/W4390099593","https://openalex.org/W4390489106","https://openalex.org/W4390659919","https://openalex.org/W4390826350","https://openalex.org/W4390873110","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4392346283","https://openalex.org/W4392607696","https://openalex.org/W4393171245","https://openalex.org/W4393906060","https://openalex.org/W4394625572","https://openalex.org/W4396505795","https://openalex.org/W4398224523","https://openalex.org/W4399039522","https://openalex.org/W4399344797","https://openalex.org/W4399375400","https://openalex.org/W4401415581","https://openalex.org/W4401806723","https://openalex.org/W4402704554","https://openalex.org/W4402727160","https://openalex.org/W4402727922","https://openalex.org/W4402774288","https://openalex.org/W4402776403","https://openalex.org/W4402952331","https://openalex.org/W4404004775","https://openalex.org/W4404600989","https://openalex.org/W4417147545"],"related_works":[],"abstract_inverted_index":{"Infrared":[0],"and":[1,12,34,59,75,85,106,135,143,210],"visible":[2,86,107],"dual-modality":[3,202],"vision":[4,95,127],"tasks":[5],"such":[6],"as":[7],"semantic":[8,56,73,119,206],"segmentation,":[9,207],"object":[10,14,208,212],"detection,":[11,209],"salient":[13,211],"detection":[15,213],"can":[16,91],"achieve":[17],"robust":[18],"performance":[19],"even":[20],"in":[21,204],"extreme":[22],"scenes":[23],"by":[24,156],"leveraging":[25],"complementary":[26,81,159],"information.":[27],"However,":[28],"most":[29],"existing":[30],"image":[31],"fusion-based":[32],"methods":[33,203],"task-specific":[35],"frameworks":[36],"exhibit":[37],"limited":[38],"generalization":[39,99],"across":[40],"multiple":[41],"tasks.":[42,214],"Moreover,":[43,164],"summing":[44],"the":[45,80,104,112,118,131,136,147,158,167,173,179,182,186,190,197,205],"general":[46,113,123],"representations":[47,124],"obtained":[48],"from":[49],"foundation":[50,108],"models":[51,109],"poses":[52],"challenges,":[53],"including":[54],"insufficient":[55],"information":[57,74,120,160],"mining":[58],"feature":[60,132,141],"fusion.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,102,129,165],"propose":[66],"a":[67],"fusion-enhanced":[68],"network,":[69],"which":[70,176],"effectively":[71],"enriches":[72],"integrates":[76],"features":[77],"based":[78],"on":[79],"characteristics":[82],"of":[83,121,161,181],"infrared":[84,105],"modalities.":[87,163,192],"The":[88],"proposed":[89,152,198],"network":[90],"extend":[92],"to":[93,110,116,171,184],"high-level":[94,126],"tasks,":[96,128],"showing":[97],"strong":[98],"capabilities.":[100],"Firstly,":[101],"adopt":[103,166],"extract":[111],"representations.":[114],"Then,":[115],"enrich":[117],"these":[122],"for":[125,140,153],"design":[130],"enhancement":[133,138],"module":[134,139,150],"token":[137],"maps":[142],"tokens,":[144],"respectively.":[145],"Besides,":[146],"attention-guided":[148],"fusion":[149,155],"is":[151],"effective":[154],"exploring":[157],"two":[162,191],"cutout&mix":[168],"augmentation":[169],"strategy":[170],"conduct":[172],"data":[174],"augmentation,":[175],"further":[177],"improves":[178],"ability":[180],"model":[183],"mine":[185],"regional":[187],"complementarity":[188],"between":[189],"Extensive":[193],"experiments":[194],"show":[195],"that":[196],"method":[199],"outperforms":[200],"state-of-the-art":[201]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-12-03T00:00:00"}